Files
skills/public/ml-huggingface-spaces.html
zeekayandHanzo Dev 9e10c1c10e Each llms index points at the other two
hanzoskills.com/llms.txt now opens with the install line, the API
reference index and the company index, so an agent that lands on any
one of the three can find the rest.

robots.txt claimed 537 documents while llms.txt counts 920. The number
is gone from robots.txt; llms.txt derives it.

public/ is regenerated from scripts/site.py, which it had fallen
behind: the copy-prompt menu and agent bar were in the generator and
not in the committed pages. tests/site.mjs passes against the result.

Co-authored-by: Hanzo Dev <[email protected]>
2026-09-11 00:27:59 -07:00

656 lines
29 KiB
HTML

<!doctype html>
<html lang="en"><head>
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
<title>ml-huggingface-spaces</title>
<meta name="color-scheme" content="dark">
<style>
/* Committed to one visual world: a dark instrument panel. No light variant —
the dot field and the hairline rules only read on black, and a naive
inversion would wash both out. Every colour is painted explicitly so the page
never borrows a host background. */
@font-face{font-family:'Zen';src:url('/fonts/Zen-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen';src:url('/fonts/Zen-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Pixel Square';src:url('/fonts/ZenPixel-Square.woff2') format('woff2');font-style:normal;font-display:swap}
:root{
--ink:#f4f4f2; --soft:#9c9c98; --faint:#6a6a66; --ground:#000; --panel:#0a0a0a;
--line:#232323; --line-hi:#3a3a3a; --accent:#f4f4f2;
--font-zen-sans:'Zen',-apple-system,BlinkMacSystemFont,"Segoe UI",Helvetica,Arial,sans-serif;
--font-zen-mono:'Zen Mono',ui-monospace,"SF Mono",SFMono-Regular,Menlo,Consolas,monospace;
--font-zen-pixel-square:'Zen Pixel Square',monospace;
--mono:var(--font-zen-mono);
--sans:var(--font-zen-sans);
/* Controls are pills and surfaces are soft, as on hanzo.ai. */
--r:999px; --r-soft:14px;
}
*{box-sizing:border-box}
html{-webkit-text-size-adjust:100%}
body{margin:0;background:var(--ground);color:var(--ink);font-family:var(--sans);
font-size:16px;line-height:1.65;-webkit-font-smoothing:antialiased}
.wrap{max-width:60rem;margin:0 auto;padding:0 1.75rem}
/* The dot field. A halftone made of one repeating radial-gradient, faded out
along the diagonal by a mask so it reads as a wave rather than wallpaper. */
/* No overflow clip here: the dot field is inset to the box already, and a clip
would cut off the copy-prompt menu. */
.hero{position:relative;border-bottom:1px solid var(--line)}
.hero::before{content:"";position:absolute;inset:0;
background-image:radial-gradient(var(--line-hi) 1px, transparent 1px);
background-size:7px 7px;
-webkit-mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
pointer-events:none}
.hero .wrap{position:relative;padding-top:5.5rem;padding-bottom:4rem}
nav{border-bottom:1px solid var(--line)}
nav .in{max-width:60rem;margin:0 auto;padding:1.1rem 1.75rem;display:flex;
justify-content:space-between;align-items:center;gap:1rem}
.brand{font-family:var(--mono);font-size:.85rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--ink);text-decoration:none;
display:inline-flex;align-items:center;gap:.6rem}
.brand i{font-style:normal;color:var(--faint)}
.mark{width:1.15em;height:1.15em;display:block;flex:0 0 auto}
nav a.up{font-family:var(--mono);font-size:.72rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--soft);text-decoration:none}
nav a.up:hover{color:var(--ink)}
h1{font-family:var(--mono);font-size:clamp(2rem,5.4vw,3.4rem);line-height:1.12;
letter-spacing:-.02em;margin:0 0 1.1rem;font-weight:500;text-wrap:balance}
h1 em{font-style:normal;color:var(--faint)}
.lede{color:var(--soft);font-size:1.05rem;max-width:52ch;margin:0 0 2.25rem}
.btns{display:flex;flex-wrap:wrap;gap:.7rem;margin:0 0 .5rem;align-items:center}
.btn{display:inline-flex;align-items:center;gap:.5rem;font-family:var(--mono);
font-size:.72rem;letter-spacing:.14em;text-transform:uppercase;
padding:.8rem 1.4rem;border:1px solid var(--line-hi);border-radius:var(--r);
color:var(--ink);text-decoration:none;background:transparent;cursor:pointer;
line-height:1.2;font-weight:400}
.btn:hover{background:#141414;text-decoration:none;border-color:var(--soft)}
.btn.solid{background:var(--ink);color:#000;border-color:var(--ink)}
.btn.solid:hover{background:#d8d8d4}
.btn .chev{width:.7em;height:.7em;flex:0 0 auto;transition:transform .15s ease}
.btn[aria-expanded="true"] .chev{transform:rotate(180deg)}
/* Copy-prompt selector. Each row copies the prompt for its own target. */
.copy{position:relative;display:inline-flex}
.menu{position:absolute;top:calc(100% + .5rem);left:0;z-index:20;min-width:21rem;
background:var(--panel);border:1px solid var(--line-hi);border-radius:var(--r-soft);
padding:.4rem;display:flex;flex-direction:column;
box-shadow:0 12px 32px rgba(0,0,0,.75)}
.menu[hidden]{display:none}
.mi{display:flex;align-items:center;gap:.7rem;width:100%;text-align:left;
padding:.62rem .8rem;border:0;border-radius:calc(var(--r-soft) - .35rem);
background:transparent;color:var(--ink);font-family:var(--mono);font-size:.76rem;
letter-spacing:.04em;text-decoration:none;cursor:pointer;line-height:1.3;
white-space:nowrap}
.mi:hover,.mi:focus-visible{background:#181818;outline:none}
.mi .mark{width:1.05rem;height:1.05rem;color:var(--soft)}
.mi:hover .mark{color:var(--ink)}
.mi u{margin-left:auto;color:var(--faint);text-decoration:none;font-size:.68rem;
letter-spacing:.1em;text-transform:uppercase}
/* Works-with bar: one scrolling row, name and mark per agent. */
.strip{border-bottom:1px solid var(--line);background:var(--panel)}
.strip .in{max-width:60rem;margin:0 auto;padding:.9rem 1.75rem;display:flex;
align-items:center;gap:1.25rem;font-family:var(--mono);font-size:.72rem;
letter-spacing:.1em;text-transform:uppercase;color:var(--faint)}
.strip b{color:var(--soft);font-weight:400;flex:0 0 auto;
border-right:1px solid var(--line);padding-right:1.25rem;align-self:stretch;
display:flex;align-items:center}
.bar{display:flex;align-items:center;gap:.5rem;flex:1 1 auto;min-width:0;
overflow-x:auto;scrollbar-width:none;scroll-snap-type:x proximity;
-webkit-overflow-scrolling:touch;
-webkit-mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent);
mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent)}
.bar::-webkit-scrollbar{display:none}
.agent{display:inline-flex;align-items:center;gap:.45rem;flex:0 0 auto;
padding:.4rem .85rem;border:1px solid var(--line);border-radius:var(--r);
color:var(--soft);white-space:nowrap;scroll-snap-align:start;
text-decoration:none;background:var(--ground)}
.agent:hover{color:var(--ink);border-color:var(--line-hi);text-decoration:none}
.agent .mark{width:.95rem;height:.95rem}
h2{font-family:var(--mono);font-size:1.1rem;letter-spacing:-.01em;margin:2.75rem 0 .75rem;font-weight:500}
h3{font-size:1rem;margin:2rem 0 .5rem;font-weight:600}
h4,h5,h6{font-size:.94rem;margin:1.5rem 0 .5rem;font-weight:600}
p{margin:0 0 1rem;max-width:70ch}
ul,ol{margin:0 0 1rem;padding-left:1.35rem;max-width:70ch}
li{margin:.22rem 0}
a{color:var(--ink);text-decoration:underline;text-underline-offset:3px;
text-decoration-color:var(--line-hi)}
a:hover{text-decoration-color:var(--ink)}
a:focus-visible{outline:1px solid var(--ink);outline-offset:3px}
code{font-family:var(--mono);font-size:.85em;background:var(--panel);
border:1px solid var(--line);border-radius:5px;padding:.1em .36em}
pre{background:var(--panel);border:1px solid var(--line);padding:1rem 1.1rem;
border-radius:var(--r-soft);overflow-x:auto;margin:0 0 1.25rem}
pre code{background:none;border:0;padding:0;font-size:.82rem;line-height:1.7}
blockquote{margin:0 0 1rem;padding-left:1rem;border-left:1px solid var(--line-hi);color:var(--soft)}
hr{border:0;border-top:1px solid var(--line);margin:2.5rem 0}
table{border-collapse:collapse;width:100%;margin:0 0 1.25rem;font-size:.92rem;
display:block;overflow-x:auto}
th,td{border:1px solid var(--line);padding:.5rem .7rem;text-align:left}
.curl{display:block;background:var(--panel);border:1px solid var(--line);
border-radius:var(--r-soft);padding:.95rem 1.1rem;font-family:var(--mono);
font-size:.8rem;color:var(--soft);overflow-x:auto;margin:0 0 2.5rem;
white-space:pre;line-height:1.9}
.curl b{color:var(--ink);font-weight:400}
.curl i{font-style:normal;color:var(--faint)}
/* index */
#q{width:100%;padding:.85rem 1.2rem;font-family:var(--mono);font-size:.85rem;color:var(--ink);
background:var(--panel);border:1px solid var(--line);border-radius:var(--r);margin:0 0 .6rem}
#q::placeholder{color:var(--faint);text-transform:uppercase;letter-spacing:.1em;font-size:.72rem}
#q:focus{outline:none;border-color:var(--soft)}
#count{color:var(--faint);font-family:var(--mono);font-size:.72rem;letter-spacing:.1em;
text-transform:uppercase;margin:0 0 2rem}
.cat{margin:2.5rem 0 .5rem;font-family:var(--mono);font-size:.7rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);border-bottom:1px solid var(--line);
padding-bottom:.45rem}
.row{display:block;padding:.6rem .9rem;margin:0 -.9rem;border-bottom:1px solid var(--line);
border-radius:var(--r-soft);text-decoration:none}
.row:hover{background:#0a0a0a}
.nm{font-family:var(--mono);font-size:.84rem;color:var(--ink);display:block}
.ds{color:var(--soft);font-size:.9rem;display:block;margin-top:.12rem}
footer{margin-top:4rem;padding:2rem 0 4rem;border-top:1px solid var(--line);
color:var(--faint);font-size:.85rem}
footer a{color:var(--soft)}
.fmap{display:grid;gap:1.75rem;grid-template-columns:repeat(auto-fit,minmax(11rem,1fr));
margin:0 0 2rem;font-size:.85rem}
.fmap b{display:block;font-family:var(--mono);font-size:.68rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);font-weight:400;margin:0 0 .6rem;
border-bottom:1px solid var(--line);padding-bottom:.4rem}
.fmap a{display:inline-block;color:var(--ink);text-decoration:none;margin:.3rem .35rem 0 0}
.fmap a:hover{text-decoration:underline}
.fmap div{color:var(--faint);line-height:1.5}
.fend{border-top:1px solid var(--line);padding-top:1.25rem;font-size:.82rem}
@media (max-width:640px){
.hero .wrap{padding-top:3.25rem;padding-bottom:2.75rem}
.btns{gap:.5rem}
.btn{padding:.75rem 1.15rem;font-size:.68rem}
.copy,.copy .btn{width:100%;justify-content:center}
.menu{left:0;right:0;min-width:0}
.strip .in{flex-direction:column;align-items:flex-start;gap:.6rem;padding:.9rem 1.75rem}
.strip b{border-right:0;padding-right:0}
.bar{width:100%}
}
</style>
<link rel="alternate" type="text/markdown" href="/ml-huggingface-spaces.md">
<link rel="icon" href="/favicon.svg">
<link rel="canonical" href="https://hanzoskills.com/ml-huggingface-spaces">
</head>
<!-- Reading this with a machine? Every page here is also plain markdown.
This one: https://hanzoskills.com/ml-huggingface-spaces.md
Index: https://hanzoskills.com/llms.txt
Corpus: https://hanzoskills.com/all.md
Append .md to any path for the markdown twin. -->
<body>
<nav><div class="in">
<a class="brand" href="/"><svg class="mark" viewBox="0 0 67 67" fill="currentColor" aria-hidden="true"><path d="M22.21 67V44.6369H0V67H22.21Z"/><path d="M66.7038 22.3184H22.2534L0.0878906 44.6367H44.4634L66.7038 22.3184Z"/><path d="M22.21 0H0V22.3184H22.21V0Z"/><path d="M66.7198 0H44.5098V22.3184H66.7198V0Z"/><path d="M66.7198 67V44.6369H44.5098V67H66.7198Z"/></svg> HANZO<i>SKILLS</i></a>
<a class="up" href="/">All skills</a>
</div></nav>
<div class="wrap">
<h1>ml-huggingface-spaces</h1><p class="lede">Deploying Gradio and Streamlit apps on HuggingFace Spaces</p><h1>HuggingFace Spaces</h1>
<p><strong>Scope</strong>: Gradio apps, Streamlit apps, Space configuration, hardware selection, secrets management <strong>Lines</strong>: ~285 <strong>Last Updated</strong>: 2025-10-25 <strong>Format Version</strong>: 1.0 (Atomic)</p>
<hr>
<h2>When to Use This Skill</h2>
<p>Activate this skill when:</p>
<ul><li>Deploying interactive ML demos and applications</li><li>Sharing models with non-technical users</li><li>Creating public or private app interfaces</li><li>Hosting Gradio or Streamlit applications</li><li>Configuring GPU-accelerated inference</li><li>Managing API keys and secrets securely</li><li>Embedding apps in websites or documentation</li><li>Setting up custom domains for apps</li></ul>
<h2>Core Concepts</h2>
<h3>Space Types</h3>
<p><strong>Gradio Spaces</strong>: Python library for ML interfaces</p>
<ul><li>Quick setup with minimal code</li><li>Pre-built components (sliders, text boxes, images)</li><li>Automatic input/output handling</li><li>Built-in examples and flagging</li><li>Real-time inference</li></ul>
<p><strong>Streamlit Spaces</strong>: Python framework for data apps</p>
<ul><li>More flexible layouts</li><li>Custom widgets and components</li><li>Session state management</li><li>Data visualization support</li><li>Multi-page apps</li></ul>
<p><strong>Static Spaces</strong>: HTML/CSS/JS only</p>
<ul><li>No server-side computation</li><li>Client-side inference with ONNX.js or TensorFlow.js</li><li>Fast loading, no compute costs</li></ul>
<h3>Space Configuration</h3>
<p><strong>README.md Metadata</strong>: Configure Space settings</p>
<pre><code class="lang-yaml">---
title: My Demo App
emoji: 🚀
colorFrom: blue
colorTo: purple
sdk: gradio # or streamlit, static
sdk_version: 4.0.0
app_file: app.py
pinned: false
license: mit
---</code></pre>
<p><strong>Hardware Options</strong>:</p>
<ul><li>CPU Basic (free): 2 vCPU, 16GB RAM</li><li>CPU Upgrade ($0.03/hr): 8 vCPU, 32GB RAM</li><li>T4 GPU ($0.60/hr): 16GB VRAM</li><li>A10G GPU ($3.15/hr): 24GB VRAM</li><li>A100 GPU ($4.13/hr): 40GB VRAM</li></ul>
<h3>Secrets Management</h3>
<p><strong>Environment Variables</strong>: Store API keys securely</p>
<ul><li>Accessible in app code via <code>os.environ</code></li><li>Not visible in public repos</li><li>Configure in Space settings UI</li><li>Support for HuggingFace tokens, OpenAI keys, etc.</li></ul>
<hr>
<h2>Patterns</h2>
<h3>Basic Gradio App</h3>
<pre><code class="lang-python">import gradio as gr
from transformers import pipeline
# Load model
classifier = pipeline(&quot;sentiment-analysis&quot;, model=&quot;distilbert-base-uncased-finetuned-sst-2-english&quot;)
# Define function
def classify_text(text):
result = classifier(text)[0]
return f&quot;{result[&#x27;label&#x27;]}: {result[&#x27;score&#x27;]:.2%}&quot;
# Create interface
demo = gr.Interface(
fn=classify_text,
inputs=gr.Textbox(lines=2, placeholder=&quot;Enter text here...&quot;),
outputs=gr.Textbox(label=&quot;Sentiment&quot;),
title=&quot;Sentiment Analysis&quot;,
description=&quot;Analyze sentiment of text using DistilBERT&quot;,
examples=[
[&quot;I love this product!&quot;],
[&quot;This is terrible.&quot;],
[&quot;It&#x27;s okay, I guess.&quot;]
]
)
# Launch app
if __name__ == &quot;__main__&quot;:
demo.launch()</code></pre>
<h3>Advanced Gradio with Multiple Inputs</h3>
<pre><code class="lang-python">import gradio as gr
from transformers import pipeline
generator = pipeline(&quot;text-generation&quot;, model=&quot;gpt2&quot;)
def generate_text(prompt, max_length, temperature, top_p):
result = generator(
prompt,
max_length=max_length,
temperature=temperature,
top_p=top_p,
num_return_sequences=1
)
return result[0][&quot;generated_text&quot;]
demo = gr.Interface(
fn=generate_text,
inputs=[
gr.Textbox(lines=3, label=&quot;Prompt&quot;),
gr.Slider(10, 200, value=50, step=10, label=&quot;Max Length&quot;),
gr.Slider(0.1, 2.0, value=0.7, step=0.1, label=&quot;Temperature&quot;),
gr.Slider(0.1, 1.0, value=0.95, step=0.05, label=&quot;Top P&quot;)
],
outputs=gr.Textbox(lines=5, label=&quot;Generated Text&quot;),
title=&quot;GPT-2 Text Generator&quot;,
examples=[
[&quot;Once upon a time&quot;, 100, 0.8, 0.95],
[&quot;The future of AI&quot;, 150, 0.7, 0.9]
]
)
demo.launch()</code></pre>
<h3>Gradio with Image Input/Output</h3>
<pre><code class="lang-python">import gradio as gr
from PIL import Image
from transformers import pipeline
# Image classification
classifier = pipeline(&quot;image-classification&quot;, model=&quot;google/vit-base-patch16-224&quot;)
def classify_image(image):
results = classifier(image)
# Format results as dictionary for label component
return {result[&quot;label&quot;]: result[&quot;score&quot;] for result in results[:5]}
demo = gr.Interface(
fn=classify_image,
inputs=gr.Image(type=&quot;pil&quot;, label=&quot;Upload Image&quot;),
outputs=gr.Label(num_top_classes=5, label=&quot;Predictions&quot;),
title=&quot;Image Classification&quot;,
description=&quot;Classify images using Vision Transformer&quot;,
examples=[&quot;cat.jpg&quot;, &quot;dog.jpg&quot;]
)
demo.launch()</code></pre>
<h3>Basic Streamlit App</h3>
<pre><code class="lang-python">import streamlit as st
from transformers import pipeline
st.title(&quot;Sentiment Analysis App&quot;)
st.write(&quot;Analyze the sentiment of your text&quot;)
# Load model (cached)
@st.cache_resource
def load_model():
return pipeline(&quot;sentiment-analysis&quot;, model=&quot;distilbert-base-uncased-finetuned-sst-2-english&quot;)
classifier = load_model()
# Input
text = st.text_area(&quot;Enter text:&quot;, height=100)
# Predict button
if st.button(&quot;Analyze&quot;):
if text:
with st.spinner(&quot;Analyzing...&quot;):
result = classifier(text)[0]
# Display result
st.success(&quot;Analysis Complete!&quot;)
col1, col2 = st.columns(2)
col1.metric(&quot;Label&quot;, result[&quot;label&quot;])
col2.metric(&quot;Confidence&quot;, f&quot;{result[&#x27;score&#x27;]:.2%}&quot;)
else:
st.warning(&quot;Please enter some text&quot;)
# Examples
st.subheader(&quot;Examples&quot;)
if st.button(&quot;Try Example: Positive&quot;):
st.write(&quot;I love this product!&quot;)
if st.button(&quot;Try Example: Negative&quot;):
st.write(&quot;This is terrible.&quot;)</code></pre>
<h3>Streamlit with Session State</h3>
<pre><code class="lang-python">import streamlit as st
from transformers import pipeline
st.title(&quot;Chat with GPT-2&quot;)
# Initialize session state
if &quot;messages&quot; not in st.session_state:
st.session_state.messages = []
# Load model
@st.cache_resource
def load_model():
return pipeline(&quot;text-generation&quot;, model=&quot;gpt2&quot;)
generator = load_model()
# Display chat history
for message in st.session_state.messages:
with st.chat_message(message[&quot;role&quot;]):
st.write(message[&quot;content&quot;])
# Chat input
if prompt := st.chat_input(&quot;Your message&quot;):
# Add user message
st.session_state.messages.append({&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: prompt})
with st.chat_message(&quot;user&quot;):
st.write(prompt)
# Generate response
with st.chat_message(&quot;assistant&quot;):
with st.spinner(&quot;Thinking...&quot;):
response = generator(prompt, max_length=100, num_return_sequences=1)[0][&quot;generated_text&quot;]
st.write(response)
# Add assistant message
st.session_state.messages.append({&quot;role&quot;: &quot;assistant&quot;, &quot;content&quot;: response})</code></pre>
<h3>Space Configuration with README</h3>
<pre><code class="lang-markdown">---
title: Sentiment Analysis Demo
emoji: 😊
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 4.0.0
app_file: app.py
pinned: false
license: mit
tags:
- sentiment-analysis
- nlp
- transformers
models:
- distilbert-base-uncased-finetuned-sst-2-english
---
# Sentiment Analysis Demo
This Space demonstrates sentiment analysis using DistilBERT.
## Features
- Real-time sentiment classification
- Confidence scores
- Example inputs
## Usage
Enter any text and click &quot;Submit&quot; to analyze sentiment.
## Model
Uses `distilbert-base-uncased-finetuned-sst-2-english` from HuggingFace.</code></pre>
<h3>Using Secrets</h3>
<pre><code class="lang-python">import os
import gradio as gr
from openai import OpenAI
# Access secret (set in Space settings)
api_key = os.environ.get(&quot;OPENAI_API_KEY&quot;)
if not api_key:
raise ValueError(&quot;OPENAI_API_KEY not found in secrets&quot;)
client = OpenAI(api_key=api_key)
def generate_with_gpt(prompt):
response = client.chat.completions.create(
model=&quot;gpt-3.5-turbo&quot;,
messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: prompt}]
)
return response.choices[0].message.content
demo = gr.Interface(
fn=generate_with_gpt,
inputs=gr.Textbox(lines=3, label=&quot;Prompt&quot;),
outputs=gr.Textbox(lines=5, label=&quot;Response&quot;),
title=&quot;GPT-3.5 Generator&quot;
)
demo.launch()</code></pre>
<h3>GPU-Accelerated Inference</h3>
<pre><code class="lang-python">import gradio as gr
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
# Check GPU availability
device = &quot;cuda&quot; if torch.cuda.is_available() else &quot;cpu&quot;
print(f&quot;Using device: {device}&quot;)
# Load model to GPU
model = AutoModelForCausalLM.from_pretrained(
&quot;meta-llama/Llama-2-7b-chat-hf&quot;,
torch_dtype=torch.float16,
device_map=&quot;auto&quot;
)
tokenizer = AutoTokenizer.from_pretrained(&quot;meta-llama/Llama-2-7b-chat-hf&quot;)
def generate(prompt, max_length=100):
inputs = tokenizer(prompt, return_tensors=&quot;pt&quot;).to(device)
with torch.no_grad():
outputs = model.generate(
**inputs,
max_length=max_length,
temperature=0.7,
top_p=0.95,
do_sample=True
)
return tokenizer.decode(outputs[0], skip_special_tokens=True)
demo = gr.Interface(
fn=generate,
inputs=[
gr.Textbox(lines=3, label=&quot;Prompt&quot;),
gr.Slider(50, 500, value=100, label=&quot;Max Length&quot;)
],
outputs=gr.Textbox(lines=10, label=&quot;Generated Text&quot;),
title=&quot;Llama 2 Chat (GPU-Accelerated)&quot;
)
demo.launch()</code></pre>
<h3>Custom Domain and Embedding</h3>
<pre><code class="lang-python">import gradio as gr
demo = gr.Interface(
fn=lambda x: x,
inputs=gr.Textbox(),
outputs=gr.Textbox(),
title=&quot;My App&quot;
)
# Launch with custom settings
demo.launch(
share=False, # Don&#x27;t create temporary share link
show_api=True, # Show API documentation
show_error=True # Show errors in UI
)</code></pre>
<p><strong>Embed in HTML</strong>:</p>
<pre><code class="lang-html">&lt;!-- Embed Space in website --&gt;
&lt;iframe
src=&quot;https://username-space-name.hf.space&quot;
frameborder=&quot;0&quot;
width=&quot;850&quot;
height=&quot;450&quot;
&gt;&lt;/iframe&gt;
&lt;!-- Embed with Gradio JS --&gt;
&lt;script type=&quot;module&quot; src=&quot;https://gradio.s3-us-west-2.amazonaws.com/3.50.0/gradio.js&quot;&gt;&lt;/script&gt;
&lt;gradio-app src=&quot;https://username-space-name.hf.space&quot;&gt;&lt;/gradio-app&gt;</code></pre>
<hr>
<h2>Quick Reference</h2>
<h3>Gradio Components</h3>
<pre><code>Component | Type | Use Case
--------------------|-------------|---------------------------
Textbox | Input | Text input/output
Slider | Input | Numeric range selection
Image | Input | Image upload
Audio | Input | Audio upload
Video | Input | Video upload
File | Input | File upload
Label | Output | Classification results
JSON | Output | Structured data
HTML | Output | Custom HTML
Plot | Output | Matplotlib/Plotly plots</code></pre>
<h3>Streamlit Components</h3>
<pre><code>Component | Function | Use Case
--------------------|-----------------------|---------------------------
text_input() | st.text_input() | Single line text
text_area() | st.text_area() | Multi-line text
slider() | st.slider() | Numeric slider
selectbox() | st.selectbox() | Dropdown selection
file_uploader() | st.file_uploader() | File upload
image() | st.image() | Display image
dataframe() | st.dataframe() | Display table
chart() | st.line_chart() | Line chart
metric() | st.metric() | Key metric display</code></pre>
<h3>Hardware Tiers</h3>
<pre><code>Tier | vCPU | RAM | GPU VRAM | Cost/Hour | Use Case
--------------|------|-------|----------|-----------|---------------------------
CPU Basic | 2 | 16GB | - | Free | Light inference
CPU Upgrade | 8 | 32GB | - | $0.03 | CPU-intensive tasks
T4 Small | 4 | 15GB | 16GB | $0.60 | Small models (&lt;7B)
A10G Large | 12 | 46GB | 24GB | $3.15 | Medium models (7-13B)
A100 Large | 12 | 142GB | 40GB | $4.13 | Large models (13B+)</code></pre>
<h3>Key Guidelines</h3>
<pre><code>✅ DO: Cache model loading with @st.cache_resource (Streamlit)
✅ DO: Provide example inputs for easier testing
✅ DO: Use secrets for API keys and tokens
✅ DO: Test locally before deploying
✅ DO: Set appropriate hardware tier for model size
✅ DO: Add loading states and error handling
❌ DON&#x27;T: Hardcode API keys in code
❌ DON&#x27;T: Load models on every function call
❌ DON&#x27;T: Use GPU for CPU-compatible models
❌ DON&#x27;T: Forget to add title and description</code></pre>
<hr>
<h2>Anti-Patterns</h2>
<h3>Critical Violations</h3>
<pre><code class="lang-python"># ❌ NEVER: Hardcode secrets
api_key = &quot;sk-xxxxxxxxxxxx&quot; # SECURITY RISK!
# ✅ CORRECT: Use environment variables
api_key = os.environ.get(&quot;OPENAI_API_KEY&quot;)</code></pre>
<p>❌ <strong>Hardcoded secrets</strong>: Security breach, exposed in public repos ✅ <strong>Correct approach</strong>: Use Space secrets in settings</p>
<h3>Common Mistakes</h3>
<pre><code class="lang-python"># ❌ Don&#x27;t: Load model on every call (Streamlit)
def predict(text):
model = pipeline(&quot;sentiment-analysis&quot;) # Reloads every time!
return model(text)
# ✅ Correct: Cache model loading
@st.cache_resource
def load_model():
return pipeline(&quot;sentiment-analysis&quot;)
model = load_model()
def predict(text):
return model(text)</code></pre>
<p>❌ <strong>No model caching</strong>: Slow, wastes resources ✅ <strong>Better</strong>: Cache with <code>@st.cache_resource</code> or load globally</p>
<pre><code class="lang-python"># ❌ Don&#x27;t: Use GPU for small models
# Running CPU-compatible model on A100 ($4/hr)
model = pipeline(&quot;sentiment-analysis&quot;, model=&quot;distilbert-base-uncased&quot;)
# ✅ Correct: Use CPU for small models
# Save costs, same performance
model = pipeline(&quot;sentiment-analysis&quot;, model=&quot;distilbert-base-uncased&quot;, device=&quot;cpu&quot;)</code></pre>
<p>❌ <strong>Wrong hardware tier</strong>: Wasted cost ✅ <strong>Better</strong>: Match hardware to model requirements</p>
<pre><code class="lang-python"># ❌ Don&#x27;t: No error handling
def predict(text):
return model(text) # Crashes on invalid input
# ✅ Correct: Handle errors gracefully
def predict(text):
try:
if not text or len(text.strip()) == 0:
return &quot;Please enter some text&quot;
return model(text)
except Exception as e:
return f&quot;Error: {str(e)}&quot;</code></pre>
<p>❌ <strong>No error handling</strong>: Poor user experience ✅ <strong>Better</strong>: Validate inputs and catch exceptions</p>
<pre><code class="lang-python"># ❌ Don&#x27;t: Missing examples
demo = gr.Interface(fn=predict, inputs=..., outputs=...)
# ✅ Correct: Provide examples
demo = gr.Interface(
fn=predict,
inputs=...,
outputs=...,
examples=[
[&quot;Example input 1&quot;],
[&quot;Example input 2&quot;]
]
)</code></pre>
<p>❌ <strong>No examples</strong>: Users don&#x27;t know what to try ✅ <strong>Better</strong>: Always provide 2-5 example inputs</p>
<hr>
<h2>Related Skills</h2>
<ul><li><code>ml/huggingface/huggingface-hub.md</code> - Managing Space repositories</li><li><code>ml/huggingface/huggingface-transformers.md</code> - Loading models for Spaces</li><li><code>frontend/elegant-design.md</code> - Improving UI/UX of custom interfaces</li><li><code>modal/modal-web-endpoints.md</code> - Alternative deployment platform</li><li><code>infrastructure/cloudflare-workers.md</code> - Edge deployment alternative</li></ul>
<hr>
<p><strong>Last Updated</strong>: 2025-10-25 <strong>Format Version</strong>: 1.0 (Atomic)</p>
<footer>
<div class="fmap">
<div><b>Build</b>
<a href="https://hanzo.app">hanzo.app</a> app builder
<a href="https://hanzo.codes">hanzo.codes</a> code with an agent
<a href="https://hanzoskills.com">hanzoskills.com</a> what an agent reads</div>
<div><b>Run</b>
<a href="https://console.hanzo.ai">console.hanzo.ai</a> cloud console
<a href="https://api.hanzo.ai">api.hanzo.ai</a> the API</div>
<div><b>Account</b>
<a href="https://hanzo.id">hanzo.id</a> sign in
<a href="https://pay.hanzo.ai">pay.hanzo.ai</a> top up
<a href="https://billing.hanzo.ai">billing.hanzo.ai</a> invoices and usage</div>
<div><b>Company</b>
<a href="https://hanzo.ai">hanzo.ai</a> canonical
<a href="https://hanzo.ventures">hanzo.ventures</a> ventures</div>
</div>
<div class="fend"><a href="/ml-huggingface-spaces.md">This page as plain text</a> · <a href="/llms.txt">Index for agents</a></div>
</footer>
</div></body></html>